Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI

TL;DR

This paper analyzes and compares ensemble mean and variance as uncertainty metrics in healthcare AI, demonstrating that ensemble mean generally outperforms variance for decision-making, validated through diabetic retinopathy diagnosis.

Contribution

It provides a theoretical and empirical comparison of uncertainty metrics in ensemble learning, guiding better decision-making in healthcare AI applications.

Findings

Ensemble mean is preferable over variance under mild assumptions.

Theoretical analysis supports empirical validation.

Case study on diabetic retinopathy confirms results.

Abstract

Ensemble learning is widely applied in Machine Learning (ML) to improve model performance and to mitigate decision risks. In this approach, predictions from a diverse set of learners are combined to obtain a joint decision. Recently, various methods have been explored in literature for estimating decision uncertainties using ensemble learning; however, determining which metrics are a better fit for certain decision-making applications remains a challenging task. In this paper, we study the following key research question in the selection of uncertainty metrics: when does an uncertainty metric outperforms another? We answer this question via a rigorous analysis of two commonly used uncertainty metrics in ensemble learning, namely ensemble mean and ensemble variance. We show that, under mild assumptions on the ensemble learners, ensemble mean is preferable with respect to ensemble variance as an uncertainty metric for decision making. We empirically validate our assumptions and theoretical results via an extensive case study: the diagnosis of referable diabetic retinopathy.